000 02833nam a2200337 i 4500
999 _c102487
_d102493
003 MY-KuUP
005 20251125111037.0
006 t||||fs|||| 000 0
007 ta
008 250502t20232023my a|||fs|||| 000 0 eng d
020 _aTHE0010022 (Local)
_qHardback
040 _aUMPSA
_beng
_cUMPSA
_erda
090 _aPSM .N33 2023 r Bc.
100 0 _aMuhammad Nadzmi Bin Md Azam,
_eauthor.
245 1 0 _aReported malicious codes incident within malaysia’s landscape: time series modelling and a timeline analysis /
_cMuhammad Nadzmi Bin Md Azam
264 1 _aKuantan, Pahang :
_bUMPSA,
_c2023
264 4 _c© 2023
300 _axi, 49 pages :
_billustrations ;
_e1 CD-ROM
336 _2rdacontent
_atext
337 _2rdamedia
_aunmediated
338 _2rdacarrier
_avolume
347 _2rda
_atext file
_bPDF
500 _aCentre for Mathematical Sciences
502 _aBachelor of Applied Science in Data Analytics with Honours -- Universiti Malaysia Pahang – 2023
504 _aIncludes bibliographical references
520 3 _aThe advancement of technology is such a marvel in these modern days. As countries embrace the vast progress of cyber-technology, the risk of cyber threats increases. Malicious codes have been one of the most menacing threats in the cyberspace, where they can damage and cost hefty damage to individuals, organisations, and governments Hence, Majlis Keselamatan Negara has developed a strategy which is known as Malaysia Cyber Security Strategy (MCSS). This strategy has four pillars to protect and sustain the perimeter of cybersecurity in Malaysia and one of the pillars is building awareness and education about cybersecurity. As an effort to align with the pillar, research involving reported malicious codes in Malaysia’s monthly data is conducted. The data will be analysed to see the outliers and recognise what the crucial factor of the outliers in the data is. Then, the outliers will be investigated, and the findings will be constructed chronologically for the timeline analysis. The data also will be forecasted to predict the trend from May 2022 until December 2024. The predictive algorithms proposed for this research are Autoregressive integrated moving average (ARIMA), Long Short Term Memory (LSTM), and NeuralProphet. The best model is chosen by the least values of mean absolute error (MAE), root mean squared error (RMSE), and mean absolute percentage error (MAPE). The outcome of this research is presented in an interactive dashboard as a deployment of this project. The dashboard is the effort to provide information on malicious codes incidents in Malaysia
610 2 0 _aCentre for Mathematical Sciences
_xDissertations
650 0 _aUniversities and colleges
_xDissertations
650 0 _aFinal Year Project
_xDissertations
942 _2lcc
_cPSM